© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59463
    Prev
    Next
    INDEX
    Explanations

    accented characters like "é" and "àï"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    umb
    -0.09
    ijľ
    -0.09
    iglia
    -0.09
    æį·
    -0.09
     кÑĢаÑģоÑĤ
    -0.08
    ombre
    -0.08
    bird
    -0.08
    å°¤åħ¶æĺ¯
    -0.08
    æķ¢
    -0.08
    å¼ĢéŨ
    -0.08
    POSITIVE LOGITS
    å¸ĺ
    0.09
    åħ¸
    0.09
    åŃĶåŃIJ
    0.09
    olated
    0.09
    åİļéĩį
    0.09
    æªĶ
    0.09
    mania
    0.09
    alon
    0.08
    å·ħå³°
    0.08
    ä»İåīį
    0.08
    Activations Density 0.030%

    No Known Activations